Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Python code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     алкого
    0.45
    اٹ
    0.45
     મતદાન
    0.43
    轳
    0.42
     CaCO
    0.42
     financiación
    0.42
    蹋
    0.42
    蜞
    0.41
    磔
    0.40
     پوچھ
    0.40
    POSITIVE LOGITS
    0.46
    IS
    0.44
    e
    0.44
    ↵
    0.43
     eBook
    0.42
    s
    0.41
    i
    0.41
     print
    0.41
    using
    0.40
    ↵↵
    0.40
    Act Density 0.006%

    No Known Activations